CN115982653A - Abnormal account identification method and device, electronic equipment and readable storage medium - Google Patents
Abnormal account identification method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN115982653A CN115982653A CN202211683510.4A CN202211683510A CN115982653A CN 115982653 A CN115982653 A CN 115982653A CN 202211683510 A CN202211683510 A CN 202211683510A CN 115982653 A CN115982653 A CN 115982653A
- Authority
- CN
- China
- Prior art keywords
- information
- abnormal
- behavior
- abnormal account
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides an abnormal account identification method, an abnormal account identification device, electronic equipment and a computer readable storage medium, wherein the method comprises the following steps: acquiring user behavior information on a preset marketing platform; classifying and dividing the user behavior information to obtain user operation behavior index information; according to the user operation behavior index information and the pre-trained risk behavior recognition network model, obtaining abnormal account recognition information; and performing right limiting processing on the abnormal account corresponding to the abnormal account identification information according to a preset abnormal behavior avoidance rule base. Through the technical scheme, the abnormal account number in the network marketing can be intelligently, simply and quickly identified and processed.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to an abnormal account identification method and apparatus, an electronic device, and a computer-readable storage medium.
Background
Various marketing means on the current network are infinite, various preferential marketing means and commodity activities provide a larger profit margin, so that a lawless person carries out illegal activity of 'pulling wool' by various means on the network; at present, the identification of various abnormal network activities and information such as related accounts thereof by means of digitization and intellectualization becomes an important link for establishing a sound anti-fraud system of each large network company at present. However, the current abnormal account identification process is complicated and not simple enough.
Content of application
The present application is directed to solving at least one of the problems in the prior art. Therefore, the embodiment of the application provides an abnormal account identification method, which can intelligently, simply and quickly identify and process the abnormal account in network marketing.
The embodiment of the application also provides an abnormal account number identification device applying the abnormal account number identification method.
The embodiment of the application also provides electronic equipment applying the abnormal account identification method.
The embodiment of the application further provides a computer readable storage medium applying the abnormal account identification method.
An embodiment of a first aspect of the present application provides an abnormal account identification method, including:
acquiring user behavior information on a preset marketing platform;
classifying and dividing the user behavior information to obtain user operation behavior index information;
acquiring abnormal account identification information according to the user operation behavior index information and a pre-trained risk behavior identification network model;
and performing the right-limiting processing on the abnormal account corresponding to the abnormal account identification information according to a preset abnormal behavior avoidance rule base.
According to some embodiments of the present application, the obtaining of the user behavior information on the preset marketing platform includes:
pre-burying data acquisition points on an activity page and a trigger button of the marketing platform;
and taking the data acquired by the data acquisition point as the user behavior information.
According to some embodiments of the present application, the classifying and dividing the user behavior information to obtain the user operation behavior index information includes:
extracting the user behavior information to obtain user behavior classification information;
and performing index extraction on the user behavior classification information to obtain the user operation behavior index information.
According to some embodiments of the application, the risk behavior recognition network model pre-trained may be obtained by:
acquiring user behavior training sample information on the marketing platform;
classifying and dividing the user behavior training sample information to obtain user operation behavior training index information;
carrying out data magnitude unified processing on the user operation behavior training index information to obtain an index map;
according to a preset abnormal account calibration strategy, performing abnormal label calibration on user data corresponding to the index map to obtain a label classification set;
performing index difference calculation processing on the user data without the abnormal label to obtain index difference information;
dividing the user data which is not marked with the abnormal label into the label classification set according to the index difference information and a preset label division strategy;
carrying out centroid calculation on the label classification set to obtain the centroid quantity, and classifying according to the centroid quantity to obtain a plurality of label classification training samples;
and according to the plurality of label classification training samples, carrying out network parameter adjustment processing on the risk behavior recognition network model.
According to some embodiments of the present application, obtaining abnormal account identification information according to the user operation behavior index information and the pre-trained risk behavior identification network model includes:
inputting the user operation behavior index information into the risk behavior recognition network model to perform label probability prediction processing to obtain abnormal label probability;
and obtaining the identification information of the abnormal account according to the probability of the abnormal label and a preset probability threshold.
According to some embodiments of the present application, the abnormal account identification information is used to characterize a user account as an abnormal account or a non-abnormal account, and the obtaining of the abnormal account identification information according to the abnormal label probability and a preset probability threshold includes:
under the condition that the probability of the abnormal label is greater than the probability threshold value, the user account corresponding to the user operation behavior index information is marked as the abnormal account;
and under the condition that the probability of the abnormal label is less than or equal to the probability threshold, marking the user account corresponding to the user operation behavior index information as the non-abnormal account.
According to some embodiments of the application, after the abnormal account corresponding to the abnormal account identification information is subjected to right limiting processing according to a preset abnormal behavior avoidance rule base, the method further includes:
and storing the user account corresponding to the abnormal account identification information into a preset time sequence database, and removing the abnormal account in the user account.
An embodiment of a second aspect of the present application provides an abnormal account identification apparatus, including:
the first processing module is used for acquiring user behavior information on a preset marketing platform;
the second processing module is used for classifying and dividing the user behavior information to obtain user operation behavior index information;
the third processing module is used for identifying a network model according to the user operation behavior index information and the pre-trained risk behavior to obtain abnormal account identification information;
and the fourth processing module is used for performing right limiting processing on the abnormal account corresponding to the abnormal account identification information according to a preset abnormal behavior avoidance rule base.
An embodiment of a third aspect of the present application provides an electronic device, including: the abnormal account identification method comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the abnormal account identification method.
A fourth aspect of the present application provides a computer-readable storage medium, where computer-executable instructions are stored, and when executed by a control processor, implement the abnormal account identification method as described above.
According to the abnormal account identification method, the abnormal account identification method at least has the following beneficial effects: in the process of identifying the abnormal account, firstly, user behavior information on a preset marketing platform is obtained, then classification and division processing are carried out on the user behavior information so as to obtain user operation behavior index information, and then the abnormal account identification information can be obtained according to the user operation behavior index information and a pre-trained risk behavior identification network model; finally, the abnormal account corresponding to the abnormal account identification information can be subjected to right limiting processing according to a preset abnormal behavior evasion library; through the technical scheme, the abnormal account number in network marketing can be intelligently, simply, conveniently and quickly identified and processed.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The above and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a flowchart of an abnormal account identification method according to an embodiment of the present disclosure;
fig. 2 is a flowchart of acquiring user behavior information in the abnormal account identification method according to the embodiment of the present application;
fig. 3 is a flowchart illustrating classification and division of user behavior information in the abnormal account identification method according to the embodiment of the present application;
fig. 4 is a flowchart of training a risk behavior recognition network model in the abnormal account recognition method according to the embodiment of the present application;
fig. 5 is a flowchart illustrating obtaining abnormal account identification information in the abnormal account identification method according to the embodiment of the present application;
fig. 6 is a flowchart illustrating a method for identifying an abnormal account according to an embodiment of the present disclosure, where the abnormal account is distinguished from a non-abnormal account;
fig. 7 is a flowchart of an abnormal account identification method according to another embodiment of the present application;
fig. 8 is a schematic diagram illustrating collecting user behavior full-volume data through a buried point according to an embodiment of the present application;
FIG. 9 is a schematic view of a marketing effect analysis provided by an embodiment of the present application;
fig. 10 is a schematic diagram of an abnormal account number identification apparatus according to an embodiment of the present application;
fig. 11 is a schematic diagram of an electronic device provided in an embodiment of the application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It is noted that while functional block divisions are provided in device diagrams and logical sequences are shown in flowcharts, in some cases, steps shown or described may be performed in sequences other than block divisions within devices or flowcharts. The terms first, second and the like in the description and in the claims, and the drawings described above, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
The embodiments of the present application will be further explained with reference to the drawings.
As shown in fig. 1, fig. 1 is a flowchart of an abnormal account identification method according to an embodiment of the present application, where the abnormal account identification method includes, but is not limited to, steps S100 to S400.
Step S100, user behavior information on a preset marketing platform is obtained;
step S200, classifying and dividing the user behavior information to obtain user operation behavior index information;
step S300, identifying a network model according to user operation behavior index information and pre-trained risk behaviors to obtain abnormal account identification information;
and step S400, performing right-limiting processing on the abnormal account corresponding to the abnormal account identification information according to a preset abnormal behavior avoidance rule base.
It should be noted that in the process of identifying an abnormal account, user behavior information on a preset marketing platform is firstly acquired, then the user behavior information is classified and divided so as to obtain user operation behavior index information, and then a network model is identified according to the user operation behavior index information and a pre-trained risk behavior so as to obtain abnormal account identification information; finally, according to a preset abnormal behavior evasion library, performing right limiting processing on the abnormal account corresponding to the abnormal account identification information; through the technical scheme, the abnormal account number in the network marketing can be intelligently, simply and quickly identified and processed.
It is to be noted that the marketing platform may be a marketing campaign web page and an APP application, and in the embodiment of the present application, user behavior information on the marketing platform may be collected, where the user behavior information may be frequency information of a user clicking a certain trigger button on a page, or frequency information of a user clicking a certain product page on a page.
It is worth noting that the user operation behavior index information can be obtained by classifying and dividing the user behavior information; illustratively, there may be wealth credits, relations and basic information classified according to the indexes, wherein the wealth credits may include index names including payment success times, activity participation times and credit scores, the relations may include index numbers of second degree relations, proportion of activity participants in the contacts and proportion of active people in the contacts, and the basic information may include index names including shopping receiving addresses, shopping network addresses and the like.
It is worth noting that the risk behavior identification network model can obtain abnormal account identification information according to the user operation behavior index information; the risk behavior recognition network model is a pre-trained model, and related network parameters are determined, so that abnormal recognition operation can be realized. The risk behavior recognition network model can be a neural network model and can be applied to abnormal account recognition operation after being pre-trained.
After the abnormal account identification information is obtained, the right limiting processing can be performed on the abnormal account corresponding to the abnormal account identification information according to a preset abnormal behavior avoidance rule base; illustratively, the abnormal account is restricted from activity participation, and is restricted from participating in high-price specified activities.
In some embodiments, as shown in fig. 2, the step S100 may include, but is not limited to, steps S110 to S120.
Step S110, pre-burying data acquisition points on an activity page and a trigger button of a marketing platform;
and step S120, taking the data acquired by the data acquisition points as user behavior information.
It should be noted that, in the process of acquiring the user behavior information, data acquisition points are pre-embedded on the activity page and the trigger button of the marketing platform, and then data acquired by the data acquisition points is used as the user behavior information. The related user behavior information can be accurately and stably obtained in a data acquisition point pre-embedding mode.
Illustratively, relevant codes are embedded into key points such as relevant content and a click button on a marketing activity webpage to obtain corresponding user behavior information, for example, a certain marketing activity page is clicked, a button of a certain activity is clicked after the page is entered, relevant user operation behaviors such as a relevant program interface are provided to obtain behavior data corresponding to the activity (for example, the user behavior full data is obtained through a java program), the embedded point obtained user behavior data is a common java program application function, and the process can be briefly described as that the user behavior full data is collected through the embedded point as shown in fig. 8.
In some embodiments, as shown in fig. 3, the step S200 may include, but is not limited to, steps S210 to S220.
Step S210, extracting the user behavior information to obtain user behavior classification information;
and step S220, index extraction is carried out on the user behavior classification information to obtain user operation behavior index information.
It should be noted that, in the process of classifying and dividing the user behavior information, the user behavior information may be extracted to obtain the user behavior classification information, and then the index extraction may be performed on the user behavior classification information to obtain the corresponding user operation behavior index information.
It is worth noting that the user operation behavior index information can be obtained by classifying and dividing the user behavior information; illustratively, there may be wealth credits, relations and basic information classified according to the indexes, wherein the wealth credits may include index names including payment success times, activity participation times and credit scores, the relations may include index numbers of second degree relations, proportion of activity participants in the contacts and proportion of active people in the contacts, and the basic information may include index names including shopping receiving addresses, shopping network addresses and the like.
Illustratively, data obtained by a webpage point burying mode is processed by a data extraction tool, and corresponding user operation behavior indexes are obtained. The relevant indexes such as the number of times of adding shopping carts, the detailed browsing of commodities, the successful payment times and the like can be specifically shown in the following table:
in some embodiments, as shown in fig. 4, the pre-trained risk behavior recognition network model may be obtained by, but is not limited to, steps S310 to S380.
Step S310, obtaining user behavior training sample information on a marketing platform;
step S320, classifying and dividing the user behavior training sample information to obtain user operation behavior training index information;
step S330, carrying out data magnitude unified processing on the user operation behavior training index information to obtain an index map;
step S340, according to a preset abnormal account calibration strategy, performing abnormal label calibration on user data corresponding to the index map to obtain a label classification set;
step S350, index difference value calculation processing is carried out on the user data without the abnormal label, and index difference value information is obtained;
step S360, dividing the user data without the abnormal label into a label classification set according to the index difference information and a preset label division strategy;
step S370, carrying out centroid calculation on the label classification set to obtain the centroid quantity, and carrying out classification according to the centroid quantity to obtain a plurality of label classification training samples;
and step S380, carrying out network parameter adjustment processing on the risk behavior recognition network model according to the plurality of label classification training samples.
It should be noted that, in the process of training the risk behavior recognition network model, user behavior training sample information on the marketing platform may be obtained first, where the user behavior training sample information and the user behavior information are information of the same nature, and are only distinguished and named for distinguishing the training process and the recognition process; classifying and dividing the user behavior training sample information to obtain user operation behavior training index information; then, carrying out data magnitude unified processing on the user operation behavior training index information to obtain an index map; then according to a preset abnormal account calibration strategy, performing abnormal label calibration on user data corresponding to the index map to obtain a label classification set; then, index difference value calculation processing is carried out on the user data without the abnormal label calibration to obtain index difference value information; dividing user data which are not marked with abnormal labels into label classification sets according to the index difference information and a preset label division strategy; secondly, carrying out centroid calculation on the label classification set to obtain the centroid quantity, and classifying according to the centroid quantity to obtain a plurality of label classification training samples; and finally, carrying out network parameter adjustment processing on the risk behavior recognition network model according to the plurality of label classification training samples.
Illustratively, in the process of training the risk behavior recognition network model, the following may be specific:
and inputting the user behavior related indexes obtained from the table into a data preprocessing program, unifying the corresponding index data in data magnitude units, and forming a corresponding index map. Abnormal account number recognition is carried out according to the following rules, and the corresponding abnormal account number is marked as 1, and the non-abnormal account number is marked as 0.
The rule for identifying the abnormal behavior can be as follows: marking users with low credit scores, which are corresponding to the activities which are participated in for multiple times and have low payment times as abnormal labels; marking users, who have a plurality of relations among the relations and are in a special list, and the activity of the relations is lower than a threshold value (a numerical value is initialized and fixed), and the number of the activity participants exceeds the threshold value, as abnormal labels; and taking a union set (a complete set) of the label data calibrated by the rule, counting the abnormal calibration times, and calibrating by taking the calibration times as reinforced labels.
Then, the numerical distances between all the customer data (without calibration label) and the relevant classification labels of the calibration data (with calibration label) and the relevant indexes thereof are calculated, and the difference of each index is calculated by using the following formula.
C i ＝arg min||x i -U j || 2
Wherein, C i Is the difference, x, of the ith unlabeled sample i Is the index value of the ith uncalibrated sample, U j Is the corresponding index value with the calibration label. Then, the difference value is divided into the data with calibration label which is nearest to the data without calibration label (with the minimum difference value) according to the difference valueAnd classifying the label corresponding to the data. And calculates its centroid by the following formula and then classifies according to the centroid number.
Wherein, mu j Representing the center of mass, U j Is the centroid of the corresponding index value with the calibration label, c (i) Is the difference, x, of the ith unlabeled sample i Is the index value of the ith non-calibrated sample.
And then inputting the corresponding calibration data into a corresponding generalized linear equation, wherein the corresponding equation is shown as the following equation.
y＝B i ∑x i
Wherein x is i Is the index value of the ith uncalibrated sample, B i Is the weighting coefficient of the ith uncalibrated sample, and y is the probability of an abnormal label.
And training a corresponding generalized linear equation to obtain a corresponding variable weight coefficient, further completing the determination of the coefficient, and performing model training according to a corresponding label training set (a mixed set of historical data with a calibration label and without the calibration label).
In some embodiments, as shown in fig. 5, the step S300 may include, but is not limited to, the steps S410 to S420.
Step S410, inputting user operation behavior index information into a risk behavior recognition network model to carry out label probability prediction processing to obtain abnormal label probability;
step S420, obtaining abnormal account identification information according to the abnormal label probability and a preset probability threshold.
It should be noted that, in the process of performing identification processing by using the risk behavior identification network model, firstly, user operation behavior index information is input to the risk behavior identification network model to perform label probability prediction processing to obtain an abnormal label probability; and then obtaining abnormal account identification information according to the abnormal label probability and a preset probability threshold.
In some embodiments, as shown in fig. 6, the abnormal account identification information is used to characterize the user account calibrated as an abnormal account or a non-abnormal account, and the step S420 may include, but is not limited to, steps S421 and S422.
Step S421, under the condition that the probability of the abnormal label is greater than the probability threshold, marking the user account corresponding to the user operation behavior index information as an abnormal account;
in step S422, under the condition that the probability of the abnormal label is less than or equal to the probability threshold, the user account corresponding to the user operation behavior index information is marked as a non-abnormal account.
It should be noted that, when the probability of the abnormal label is greater than the probability threshold, the user account corresponding to the user operation behavior index information is marked as an abnormal account; and under the condition that the probability of the abnormal label is less than or equal to the probability threshold, the user account corresponding to the user operation behavior index information is marked as a non-abnormal account.
In some embodiments, as shown in fig. 7, step S500 may be further included, but not limited to, after step S400 is performed.
Step S500, storing the user account corresponding to the abnormal account identification information into a preset time sequence database, and eliminating the abnormal account in the user account.
It should be noted that after the authorization processing is performed on the abnormal account corresponding to the abnormal account identification information, the user account corresponding to the abnormal account identification information may also be stored in a preset time sequence database, and the abnormal account in the user account may be removed. The marketing effect of the evaluated marketing campaign may also be calculated based on the following formula, and its marketing effect analysis diagram may be as shown in fig. 9.
r i ＝CC i /C i
Wherein, CC i Number of converted users representing activity i, C i Number of users representing activity i, r i Representing the user conversion rate for activity i.
As shown in fig. 10, an embodiment of the second aspect of the present application provides an abnormal account number identification apparatus, including:
the first processing module 100 is configured to acquire user behavior information on a preset marketing platform;
the second processing module 200 is configured to classify and divide the user behavior information to obtain user operation behavior index information;
the third processing module 300 is configured to identify a network model according to the user operation behavior index information and the pre-trained risk behavior, and obtain abnormal account identification information;
the fourth processing module 400 is configured to perform right limiting processing on the abnormal account corresponding to the abnormal account identification information according to a preset abnormal behavior avoidance rule base.
It should be noted that, because the abnormal account identification apparatus in this embodiment is based on the same inventive concept as the abnormal account identification method in the foregoing embodiment, corresponding contents in the method embodiment are also applicable to this system embodiment, and are not described herein again.
In addition, as shown in fig. 11, an embodiment of the present application also provides an electronic device 700, including: memory 720, processor 710, and computer programs stored on memory 720 and operable on processor 710.
The processor 710 and the memory 720 may be connected by a bus or other means.
Non-transitory software programs and instructions required to implement the abnormal account identification method of the above-described embodiment are stored in the memory 720, and when executed by the processor 710, the abnormal account identification method of each of the above-described embodiments is performed, for example, the method steps S100 to S400 in fig. 1, the method steps S110 to S120 in fig. 2, the method steps S210 to S220 in fig. 3, the method steps S310 to S380 in fig. 4, the method steps S410 to S420 in fig. 5, the method steps S421 to S422 in fig. 6, and the method step S500 in fig. 7 described above are performed.
In the description herein, reference to the description of the terms "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the application, the scope of which is defined by the claims and their equivalents.
Claims (10)
1. An abnormal account identification method is characterized by comprising the following steps:
acquiring user behavior information on a preset marketing platform;
classifying and dividing the user behavior information to obtain user operation behavior index information;
acquiring abnormal account identification information according to the user operation behavior index information and a pre-trained risk behavior identification network model;
and performing the right-limiting processing on the abnormal account corresponding to the abnormal account identification information according to a preset abnormal behavior avoidance rule base.
2. The abnormal account identification method according to claim 1, wherein the acquiring of the user behavior information on the preset marketing platform includes:
pre-burying data acquisition points on an activity page and a trigger button of the marketing platform;
and taking the data acquired by the data acquisition point as the user behavior information.
3. The abnormal account identification method according to claim 1, wherein the classifying and dividing the user behavior information to obtain user operation behavior index information includes:
extracting the user behavior information to obtain user behavior classification information;
and performing index extraction on the user behavior classification information to obtain the user operation behavior index information.
4. The abnormal account identification method according to claim 1, wherein the risk behavior identification network model pre-trained is obtained by:
acquiring user behavior training sample information on the marketing platform;
classifying and dividing the user behavior training sample information to obtain user operation behavior training index information;
carrying out data magnitude unified processing on the user operation behavior training index information to obtain an index map;
according to a preset abnormal account calibration strategy, performing abnormal label calibration on user data corresponding to the index map to obtain a label classification set;
performing index difference calculation processing on the user data without the abnormal label calibrated to obtain index difference information;
dividing the user data which is not marked with the abnormal label into the label classification set according to the index difference information and a preset label division strategy;
carrying out mass center calculation on the label classification set to obtain mass center quantity, and classifying according to the mass center quantity to obtain a plurality of label classification training samples;
and according to the plurality of label classification training samples, carrying out network parameter adjustment processing on the risk behavior recognition network model.
5. The abnormal account identification method according to claim 1, wherein obtaining abnormal account identification information according to the user operation behavior index information and a pre-trained risk behavior identification network model comprises:
inputting the user operation behavior index information into the risk behavior recognition network model to perform label probability prediction processing to obtain abnormal label probability;
and obtaining the identification information of the abnormal account according to the probability of the abnormal label and a preset probability threshold.
6. The abnormal account identification method according to claim 5, wherein the abnormal account identification information is used for characterizing that a user account is calibrated as an abnormal account or a non-abnormal account, and the obtaining of the abnormal account identification information according to the abnormal label probability and a preset probability threshold includes:
under the condition that the probability of the abnormal label is greater than the probability threshold value, the user account corresponding to the user operation behavior index information is marked as the abnormal account;
and under the condition that the probability of the abnormal label is less than or equal to the probability threshold, marking the user account corresponding to the user operation behavior index information as the non-abnormal account.
7. The abnormal account identification method according to claim 1, wherein after the abnormal account corresponding to the abnormal account identification information is subjected to the right-limiting processing according to a preset abnormal behavior avoidance rule base, the method further comprises:
and storing the user account corresponding to the abnormal account identification information into a preset time sequence database, and removing the abnormal account in the user account.
8. An abnormal account number recognition device, comprising:
the first processing module is used for acquiring user behavior information on a preset marketing platform;
the second processing module is used for classifying and dividing the user behavior information to obtain user operation behavior index information;
the third processing module is used for identifying a network model according to the user operation behavior index information and the pre-trained risk behavior to obtain abnormal account identification information;
and the fourth processing module is used for performing the right-limiting processing on the abnormal account corresponding to the abnormal account identification information according to a preset abnormal behavior avoidance rule base.
9. An electronic device, comprising: memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the abnormal account identification method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium storing computer-executable instructions, which when executed by a control processor implement the abnormal account identification method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211683510.4A CN115982653A (en) | 2022-12-27 | 2022-12-27 | Abnormal account identification method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211683510.4A CN115982653A (en) | 2022-12-27 | 2022-12-27 | Abnormal account identification method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115982653A true CN115982653A (en) | 2023-04-18 |
Family
ID=85975454
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211683510.4A Pending CN115982653A (en) | 2022-12-27 | 2022-12-27 | Abnormal account identification method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115982653A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116433338A (en) * | 2023-06-15 | 2023-07-14 | 青岛网信信息科技有限公司 | Product marketing inventory protection method, medium and system |
-
2022
- 2022-12-27 CN CN202211683510.4A patent/CN115982653A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116433338A (en) * | 2023-06-15 | 2023-07-14 | 青岛网信信息科技有限公司 | Product marketing inventory protection method, medium and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108363821A (en) | A kind of information-pushing method, device, terminal device and storage medium | |
| CN111160473A (en) | Feature mining method and device for classified labels | |
| CN113656558B (en) | Method and device for evaluating association rule based on machine learning | |
| CN109685537B (en) | User behavior analysis method, device, medium and electronic equipment | |
| CN111882420A (en) | Generation method of response rate, marketing method, model training method and device | |
| CN112785441B (en) | Data processing method, device, terminal equipment and storage medium | |
| CN112116168B (en) | User behavior prediction method and device and electronic equipment | |
| CN112348417A (en) | Marketing value evaluation method and device based on principal component analysis algorithm | |
| CN113469730A (en) | Customer repurchase prediction method and device based on RF-LightGBM fusion model under non-contract scene | |
| CN110956303A (en) | Information prediction method, device, terminal and readable storage medium | |
| CN114612251A (en) | Risk assessment method, device, equipment and storage medium | |
| CN115982653A (en) | Abnormal account identification method and device, electronic equipment and readable storage medium | |
| CN114399379A (en) | Artificial intelligence-based collection behavior recognition method, device, equipment and medium | |
| CN116739811A (en) | Enterprise financial information intelligent management system and method for self-adaptive risk control | |
| CN114297447B (en) | Electronic certificate marking method and system based on epidemic prevention big data and readable storage medium | |
| CN108197795A (en) | The account recognition methods of malice group, device, terminal and storage medium | |
| CN113807728A (en) | Performance assessment method, device, equipment and storage medium based on neural network | |
| CN116452212B (en) | Intelligent customer service commodity knowledge base information management method and system | |
| CN112487284A (en) | Bank customer portrait generation method, equipment, storage medium and device | |
| CN115577172A (en) | Article recommendation method, device, equipment and medium | |
| KR101960863B1 (en) | System of valuation of technology | |
| CN115293867A (en) | Financial reimbursement user portrait optimization method, device, equipment and storage medium | |
| CN114626940A (en) | Data analysis method and device and electronic equipment | |
| CN114493851A (en) | Risk processing method and device | |
| CN113420789A (en) | Method, device, storage medium and computer equipment for predicting risk account |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |